* Let every chat of an agent use the browser tabs of the agent
Main chats and side threads of an agent can now use all browser tabs of
that agent. list_tabs shows the chat that opened each tab and tells when
another chat uses a tab now. Takeover, submit_secret and list_logins use
the same rule. Channel and messaging threads still use only their own
tabs and the tabs shared with an @ tag.
* Keep channel tabs out of other chats and make the working hint reliable
The main chat and side threads use only the tabs that the main chat, a
side thread or no chat opened. Tabs of a channel or a messaging thread
stay out of these chats unless a person tags them with @.
otherChatWorking now also uses the last chat that used each tab in the
last 2 minutes, because control sessions end 1.2 s after a call.
A takeover from one chat no longer deletes the held takeover result of
another chat. list_tabs looks up each chat once per call.
The browser user-control E2E now covers the cross-chat access.
* Keep a held takeover result for each chat of a tab
Held takeover results used only the tab id as the key. When two chats of
one agent took over the same tab, the second result replaced the first.
The key is now the tab id and the thread id.
* Remove code comments and add the no-comments rule
Remove the comments from first-party code and configuration files:
TS/JS, JSX, CSS, SQL migrations, Swift, Kotlin, Gradle, shell,
Docker, systemd, Nix, YAML, TOML, JSONC and GritQL.
Keep only what a tool reads: license headers, shebangs, compiler
and lint directives, JSDoc types in plain .js files, generated file
headers, GritQL scope lines, the install-server.sh help text and the
openbot-boat-pre-stop marker. Vendored code, fixtures and released
schemas keep their comments.
Add the rule to AGENTS.md, and change the docs that asked for
comments. Add two i18n keys that only comments named to
RELEASED_SOURCE_KEYS.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* Keep comments that are data in strings
The benchmark task files in opencode-free-models-bench.ts tell the
model what each function must do. The sample file and HTML page in
the two stories are display content. Put their comments back.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* Keep released migrations and mobile native inputs unchanged
check:migrations compares each released migration with v0.73.0 byte
for byte, so restore src/backend/migrations. A change to a native
build input of apps/mobile makes a new runtime version, so restore
those files and the extra fingerprint sources.
List these files and the comment markers that a tool reads in
AGENTS.md. Remove the last requests for comments in
src/renderer/AGENTS.md.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* Close security gaps found in the security review
- Team API: a member does not see or use the browser tabs of an agent at
`none`, and cannot open a tab for that agent. Routes and events use
the same test.
- Remote viewer proxy: each joined server has its own path secret, and
HTTP reaches only the remote-screen routes.
- Logging: redact tokens after any Authorization scheme, name and value
pairs, Google OAuth tokens, Telegram bot tokens and webhook addresses.
- Network guard: refuse the rest of ::/64 (IPv4-compatible and SIIT).
- Pi on Windows: run where.exe from System32, not from the agent folder.
- Mobile: delete the phone copy when the session expires, and at a start
with no session.
- Signal: compare the metrics token in constant time. TURN: deny all of
::/96 and the IPv4-mapped range as peers.
- Tests: a closed-agent tab check in the Team API routes E2E, IPv6 cases
in the MCP OAuth E2E, and a new remote viewer proxy E2E in CI.
* Stop tab access at once when an agent closes to a member
- When the roles close an agent to a member, the host gives back that
member's hold of the agent's tabs and closes the member's live views.
- The browser control state and its event show only the tabs that the
member can see.
- The TURN server refuses all of ::/64, also the SIIT range.
* Add Teach a task: record browser steps and send them to the agent as a skill request
* Discard a teach recording when the agent changes, and use the contract step type on the host
* Give a correct error when another person controls the tab at the start of a teach recording
* Keep the draft text when the teach steps go to the draft
* Let a user tag browser tabs and threads in chat
The @ picker of the chat composer now has sections for agents, browser
tabs and threads. A tag becomes a chip in the message.
- A tab tag lists only the tabs of the agent of the chat. When the user
sends it, the host shares that tab with the target thread of the same
agent, so a side thread can use a tab of the main chat.
- A thread tag gives the agent one short line: the title, the task id,
the state and the start of the result. The agent reads more with
history_read or history_search and the new optional taskId.
- The stored text keeps the marker. The marker expands at delivery, so
the agent gets the current title and state.
- A click on a chip opens the tab page or the thread.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* Share a tagged tab when its prompt is built
- Share the tab with the public thread that gets the prompt, not when
the message is queued. A queued message can move or change.
- Use the strict name rule for tab and thread titles.
- A popup keeps the shares of its opener tab.
- A tag from a teammate shows as a name only.
- The picker lists only tabs that have an owner agent.
- Use browserDisplayUrl in the picker.
- Make the thread question in chat-tags-e2e exact.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* Keep TaggedThreadState private to delivery-content
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* Keep phones quiet while the computer has input in any app
Before, a host kept the phone quiet only for 30 seconds after a send,
an answer or typing in the desktop app that is joined to it. Use of
another app on the same computer did not count, so the phone notified
while the user worked at the computer.
The desktop app now reads the system idle time and tells each joined
host when the computer last had input, through the new optional
capability computer-activity-v1. It tells a host only when it shows the
events of that host itself. The host keeps the time in memory for the
away time only.
OPENBOT_DEV_AWAY_SECONDS sets a different away time in an unpackaged
app, for tests.
* Do not export ComputerActivityOptions
Only remote-server-manager.ts uses the type, and knip fails on an unused export.
* Keep the no-phone pause when a host stops being a target
The pause was in the report of each target, and a target change deleted
that report. So a host that answered that it notifies no phone of the
member learned of new input each time the member went back to the
OpenBot window. The pause now has its own map, and only its end time
removes it.
* Say how long a host keeps the computer input time
The host uses the time for the away time only, but removes an old time
only at the next report or at the end of the session. PRIVACY.md said
that it keeps the time for 30 seconds.